© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2957
    Prev
    Next
    INDEX
    Explanations

    references to legal standards related to assessing the probability of prejudice or outcome in criminal or appellate law cases

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     law
    -0.63
     CURIAM
    -0.55
    law
    -0.52
     Law
    -0.51
     paragraphs
    -0.50
     recev
    -0.50
     legal
    -0.49
     court
    -0.48
     federal
    -0.48
     judicial
    -0.48
    POSITIVE LOGITS
    UrlResolution
    0.81
    yntaxException
    0.75
    IntoConstraints
    0.73
    aternion
    0.71
    +#+#
    0.71
    LElement
    0.68
    HostException
    0.68
    <bos>
    0.67
    StreetMap
    0.67
    expandindo
    0.67
    Activations Density 2.336%

    No Known Activations